Hacker News Reader

Comment by esafak | Hacker News Reader

At least Ilya's crew was working on alignment (https://openai.com/blog/introducing-superalignment). If only the rank-and-file had been more vocally supportive of that, instead of enthusiastically boarding the Altman train. Look where that train is headed...

View on HN

Alignment with whose values? Altmans? Ilya's? Humanity's? The USA? Some unspecified ideal? I have a really hard time passing the responsibility for such massive impact decisions to a bunch of talented technicians who have already demonstrated a poor command of ethics. The more likely outcome is that it will end up being 'alignment with whoever has the money', and that's a recipe for some bad stuff in our future.

Geoffrey Hinton would love this news.

Queue the immortal soldiers?

I put all my hope for humanity in the Open Source AI movement. As a liberal capitalist freedom thinker who likes alt-mags and torrent files.

Allowing the AI Ethicists to decide what is and is not aligned is to consign our future to a new dark age of rule by clergy.

Just fucking go put on 2112 - Rush already.

The people with the most money are the citizens of the United States, to be clear.

Good one.

My point is that Americans can and will overthrow any regime that makes their lives hard(er). It'll take a LOT to encourage them, but they will do so, and there's even ways to do so peacefully and without violence. Elections, then state laws, then an Article V convention.

Not if they take away or keep watering down the 2nd amendment.

?? All I've seen when it comes to 2A is a strengthening thereof, espcially downstream of Bruen

> Look where that train is headed...

https://en.wikipedia.org/wiki/Metalhead_(Black_Mirror)

What's the benefit of a military ai that's more aligned to the military's goals?

If you're against ai military, wouldn't you want the alignment to be poor?

Alignment to _what_? Humans aren't aligned without AI, what exactly will AI be aligned to?

That's like asking "programs that execute within a predictable scope for what?"

For whatever they're being written for. Alignment's goal is to have models to do what they're being trained to do and not other random things. It won't be uniform; for example, determining "what does inappropriate mean" will vary between countries.

So it sounds like Ilya is making rifles with more precision, then.

More like self driving cars that stay within the lines instead of treating everything as an offroad opportunity. If you wanna use rifles from them or mod them to run people over, that's on you right?

Aligned to its creator's specifications. It's value neutral, but constraints are a precondition for avoiding pathological behavior.

Reply on news.ycombinator.com